Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint, openWorldHint=false, and idempotentHint, covering the safety profile. The description adds a genuinely non-obvious behavior: totals are computed over the FULL filtered dataset, not the returned page, so grand_total is safe to quote even when groups are paginated — critical for correct reporting. This goes beyond the annotations and contradicts none of them.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two sentences with zero waste: the first states purpose, the second delivers the key behavioral guarantee. The critical pagination caveat is front-loaded and densely informative.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For an 8-param, 4-mode tool with no output schema, the description covers the main footgun (pagination semantics) and names the four report domains, so an agent can select the right kind. However, per-kind return shapes beyond grand_total are not described, leaving the response structure to inference. It is adequate for selection and invocation, though richer per-kind output detail would close the gap.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

With 63% schema description coverage, most params (kind, statuses, dates, billable_only) are already documented in the schema. The description adds meaning to limit/offset by clarifying that pagination affects only the group list, not the totals, and it maps the four report domains to the kind enum values. project_id remains undocumented in both schema and description.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a clear verb+resource: it fetches 'server-side aggregated reports across time, revenue, pipeline and utilization', naming the four report domains that map directly to the kind enum. The 'server-side aggregated' qualifier distinguishes it from raw-data sibling endpoints like timelog_get_entries or projects_get_finance, though no sibling is named explicitly.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies when to use it — any time an agent needs aggregated totals rather than raw records — but never states this explicitly and names no alternatives or exclusions. The grand_total guarantee hints at a reporting use case, yet an agent must infer that this is the aggregation tool versus projects_get_finance or timelog_get_entries. No explicit when/when-not routing guidance is provided.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.